An Enhanced Feature Pyramid Object Detection Network for Autonomous Driving
Source abstract
Abstract
Feature Pyramid Network (FPN) builds a high-level semantic feature pyramid and detects objects of different scales in corresponding pyramid levels. Usually, features within the same pyramid levels have the same weight for subsequent object detection, which ignores the feature requirements of different scale objects. As we know, for most detection networks, it is hard to detect small objects and occluded objects because there is little information to exploit. To solve the above problems, we propose an Enhanced Feature Pyramid Object Detection Network (EFPN), which innovatively constructs an enhanced feature extraction subnet and adaptive parallel detection subnet. Enhanced feature extraction subnet introduces Feature Weight Module (FWM) to enhance pyramid features by weighting the fusion feature map. Adaptive parallel detection subnet introduces Adaptive Context Expansion (ACE) and Parallel Detection Branch (PDB). ACE aims to generate the features of adaptively enlarged object context region and original region. PDB predicts classification and regression results separately with the two features. Experiments showed that EFPN outperforms FPN in detection accuracy on Pascal VOC and KITTI datasets. Furthermore, the performance of EFPN meets the real-time requirements of autonomous driving systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Video Surveillance and Tracking Methods · Advanced Image and Video Retrieval Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Graduate School of Information, Production and Systems, Waseda University, Fukuoka 8080135, Japan
Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
References (27)
Show source-provided references
1. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
2. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
3. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
4. Selective search for object recognition10.1007/s11263-013-0620-5 ↗
5. Ren, S., He, K., Girshick, R.B., and Sun, J. (2015, January 7–12). Faster R-CNN: Towards real-time object detection with region proposal networks. Proceedings of the Conference on Neural Information Processing Systems, Montreal, QC, Canada.
6. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
7. Girshick, R.B. (2015, January 7–12). Fast R-CNN. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/ICCV.2015.169 ↗
8. Dai, J., Li, Y., He, K., and Sun, J. (2016, January 5–10). R-FCN: Object detection via region-based fully convolutional networks. Proceedings of the Conference on Neural Information Processing Systems, Barcelona, Spain.
9. Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., and Sun, J. (2017). Light-head r-cnn: In defense of two-stage object detector. arXiv.
10. Cai, Z., Fan, Q., Feris, R.S., and Vasconcelos, N. (2016, January 11–14). A unified multi-scale deep convolutional neural network for fast object detection. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_22 ↗
11. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S.E., Fu, C., and Berg, A.C. (2016, January 11–14). SSD: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
12. Kong, T., Yao, A., Chen, Y., and Sun, F. (July, January 26). Hypernet: Towards accurate region proposal generation and joint object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
13. Bell, S., Zitnick, C.L., Bala, K., and Girshick, R.B. (July, January 26). Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
14. Lin, T., Dollár, P., Girshick, R.B., He, K., Hariharan, B., and Belongie, S.J. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
15. Fu, C., Liu, W., Ranga, A., Tyagi, A., and Berg, A.C. (2017). DSSD: Deconvolutional single shot detector. arXiv.
16. Kong, T., Sun, F., Yao, A., Liu, H., Lu, M., and Chen, Y. (2017, January 21–26). RON: Reverse connection with objectness prior networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.557 ↗
17. Shrivastava, A., Sukthankar, R., Malik, J., and Gupta, A. (2016). Beyond skip connections: Top-down modulation for object detection. arXiv.
18. Hu, J., Shen, L., and Sun, G. (2018, January 18–22). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
19. Roy, A.G., Navab, N., and Wachinger, C. (2018, January 16–20). Concurrent spatial and channel ‘squeeze & excitation’ in fully convolutional networks. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Granada, Spain.10.1007/978-3-030-00928-1_48 ↗
20. Gidaris, S., and Komodakis, N. (2015, January 7–13). Object detection via a multi-region and semantic segmentation-aware CNN model. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.135 ↗
21. Zhu, Y., Urtasun, R., Salakhutdinov, R., and Fidler, S. (2015, January 7–12). segdeepm: Exploiting segmentation and context in deep neural networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.
22. Wang, S. (2017, January 4–7). PCN: Part and context information for pedestrian detection with cnns. Proceedings of the British Machine Vision Conference, Oxford, UK.10.5244/C.31.34 ↗
23. Chen, X., and Zhu, Y. (2015, January 7–12). 3d object proposals for accurate object class detection. Proceedings of the Conference on Neural Information Processing Systems, Montreal, QC, Canada.
24. The pascal visual object classes (voc) challenge10.1007/s11263-009-0275-4 ↗
25. Geiger, A., Lenz, P., and Urtasun, R. (2012, January 16–21). Are we ready for autonomous driving? The kitti vision benchmark suite. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.10.1109/CVPR.2012.6248074 ↗
26. Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (July, January 26). The cityscapes dataset for semantic urban scene understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
27. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 21–26). Mask r-cnn. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/ICCV.2017.322 ↗